User Guide

How to customize pre-built
AI pipelines on WindyFlo

Learn how to customize pre-built AI pipelines and create your own AI functionalities without writing a single line of code.

Try now

Who is this guide for?

Developers, product managers, and entrepreneurs who want to integrate AI functionality into their apps or websites without complicated coding or expensive computing resources.

First, sign up or log-in to WindyFlo.

1. Fork a pre-built pipeline.

1) On the menu, go to Pipeline Hub and select a pipeline.

Search or scroll down to select a pipeline that is close to the one you're trying to build.

On the menu, go to Pipeline Hub and select a pipeline.

On the menu, go to Pipeline Hub and select a pipeline.

2) Review the pre-built pipeline and click 'Fork.'

By 'forking,' you will

Review the pre-built pipeline and click 'Fork.'

2. Customize the pipeline.

1) Fill in the pipeline details, then click Create AI Model Pipeline.

  • Pipeline Name: Name your pipeline.
  • Description: Summarize the purpose of the pipeline.
  • Tags: Add tags to make your pipeline easier to discover.
  • Public/Private: Choose whether to keep the pipeline public or private*.
    • (*Private pipelines are available for paid plans users.)

Fill in the pipeline details, then click Create AI Model Pipeline.

2) Select Pipeline on the left-side menu.

This will open your workspace for this pipeline.

Select Pipeline on the left-side menu.

3) Add new nodes or modify the parameters of existing nodes to customize the pipeline.

  • Inputs are on the left, and outputs are on the right of each node.
  • Click and drag to connect node points with matching input/output types.

Add new nodes or modify the parameters of existing nodes to customize the pipeline.

4) Connect the nodes.

For instance, if you selected the Document Retrieval Q&A pipeline, you can upload your own [.txt] or [.pdf] files by clicking on the upload option in the Text File or PDF File nodes.

Connect the nodes.

3. Save and test-run.

1) Click Save, and then click Run.

Click Save, and then click Run.

2) Type a command to test the pipeline.

Type a command to test the pipeline.

4. Share the Pipeline

To share via API

1) Save your pipeline, and then click 'Embed as API.'

To make it accessible via API or embedded on a website.

Save your pipeline, and then click 'Embed as API.'

2) Choose your preferred language (HTML, React, Python, JavaScript, or CURL) and copy-paste the generated code into your service.

Choose your preferred language (HTML, React, Python, JavaScript, or CURL) and copy-paste the generated code into your service.

To use as chatbot

1) Alternatively, to share it as a chatbot with no additional integration, select Share Chatbot.

  • This feature is only available for pipelines that function as chatbots.
  • Pipelines designed for data processing may not support this feature.

Alternatively, to share it as a chatbot with no additional integration, select Share Chatbot.

2) Customize the chatbot settings (e.g., title, welcome message) and click the new tab icon to launch.

  • Left icon: Copy link
  • Right icon: Open link

Customize the chatbot settings (e.g., title, welcome message) and click the new tab icon to launch.

3) Test your chatbot by entering a query in the "Type your question..." field.

  • Once testing is complete, copy the link and share it with your audience!

Test your chatbot by entering a query in the "Type your question..." field.

Start building custom AI features
without coding or AI expertise.